© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 28149
    Prev
    Next
    INDEX
    Explanations

    music and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spears
    -0.10
    uby
    -0.09
    åIJĮçŃī
    -0.09
     HAPP
    -0.09
     stag
    -0.09
     ÑĤÑĢебÑĥеÑĤÑģÑı
    -0.09
    æµ·éĩı
    -0.09
    èĢģåŃIJ
    -0.09
    arto
    -0.08
    inand
    -0.08
    POSITIVE LOGITS
    廨
    0.09
    秦çļĩ
    0.09
    åľ¨è¿ĩ渡
    0.08
    åĪ°åľº
    0.08
    adow
    0.08
    à¸Ħà¸Ńย
    0.08
    ç§ijå°Ķ
    0.08
     Cul
    0.08
    æĥ®
    0.08
    身穿
    0.08
    Activations Density 0.029%

    No Known Activations